This paper deals with the integration of domain knowledge to improve the landcover classification of a sequence of images. This new approach consists in representing the plot of land as a dynamic system and in modeling its evolution (knowledge about crop cycles, rotations and farmer practices) with the timed automata formalism. The main feature of this work is to improve the classification prov...

Christiana Care Health System implemented a Care Management Guideline for Alcohol Withdrawal Symptom Management, which provided direction for inpatient screening for alcohol withdrawal risk, assessment, and treatment. Nurses educated on its use expressed confusion with the use of the assessment tools, pharmacokinetics, and pathophysiology of alcohol withdrawal and delirium tremens. Reeducation ...

The growing number of statistical topic models led to the need to better evaluate their output. Traditional evaluation means estimate the model’s fitness to unseen data. It has recently been proven than the output of human judgment can greatly differ from these measures. Thus the need for methods that better emulate human judgment is stringent. In this paper we present a system that computes th...

Word embeddings learned on unlabeled data are a popular tool in semantics, but may not capture the desired semantics. We propose a new learning objective that incorporates both a neural language model objective (Mikolov et al., 2013) and prior knowledge from semantic resources to learn improved lexical semantic embeddings. We demonstrate that our embeddings improve over those learned solely on ...

We report on a series of experiments with probabilistic context-free grammars predicting English and German syllable structure. The treebank-trained grammars are evaluated on a syllabification task. The grammar used by Müller (2002) serves as point of comparison. As she evaluates the grammar only for German, we reimplement the grammar and experiment with additional phonotactic features. Using b...

We demonstrate the need for reuse in today's software development organisations in the light of widely accepted literature. Based on this need, we introduce the reuse processes and identify the knowledge dependent processes involved. We provide an introduction to the KM process model developed at VTT and describe the process of continuous improvement integrated to it. We establish a link betwee...

We examined whether playing a computerized fraction game, based on the integrated theory of numerical development and on the Common Core State Standards' suggestions for teaching fractions, would improve children's fraction magnitude understanding. Fourth and fifth-graders were given brief instruction about unit fractions and played Catch the Monster with Fractions, a game in which they estimat...

In this paper we present a method to enrich the hypothesis language which is used to construct the bottom clause. This approach, which is embedded in the Aleph system, is based on numerical fixed subintervals and categorical subsets. Each subinterval/subset contains values, for each attribute which is predefined, that are related with the example to saturate. The enriched language allows to red...

The Jacobian of a neural network, or the derivative of the output with respect to the input, is a versatile object with many applications. In this paper we discuss methods to use this object efficiently for knowledge transfer. We first show that matching Jacobians is a special form of distillation, where noise is added to the input. We then show experimentally that we can perform better distill...